Over the past years the Bionic Learning Network, a consortium of universities, institutes and development companies run by German automation giant Festo, has been turning out impressive robotic artifacts. Festo thinks of robots like the AquaPenguin, AquaRay and AquaJelly pictured above as technology demonstrators that help identify bionic principles. These principles in turn may be applicable in their next generation of automation products. In the latest episode of the Robots podcast, Markus Fischer, head of the Bionic Learning Network project and head of Festo's Corporate Design explains how Festo transfers technologies from biomimetic research to actual products. In the second part of this episode Victor Zykov, very well known for his work on Resilient Introspective Machines with Hod Lipson, talks more about the role of bio-inspiration as well as his favorite topic, modular robots. Zykov explains his work on his bio-inspired Molecubes (see some previous posts), and tells us how Festo may use modular robots to construct the adaptable factories of the future. Tune in!

Robots use all kinds of embedded processors. New processors are being created all the time. Writing software for all those processor requires a compiler and the most commonly used compiler is GNU GCC, originally created by Richard Stallman that made the Free Software and Open Source movements possible. The trouble is, a lot of work is involved in optimizing a complex compiler like GCC for every new processor that turns up. What if we could use AI and machine learning techniques to do all that work? This idea was explored by a group of EU research organizations. The result is MILEPOST GCC 4.4.0, the first machine learning enabled, self-tuning compiler that can adapt to any architecture using an iterative feedback-directed process. From the IBM press release:

Initial IBM experiments conducted on IBM System p servers achieved an average 18 percent performance improvement on embedded-application benchmarks...it normally takes application developers many months to get their software running at an acceptable level of performance. Milepost GCC can reduce the amount of time it takes to reach that level by a factor of 10.

The diagram above compares a block diagram of the current GCC with MILEPOST GCC. At present MILEPOST GCC is a research compiler only but because it's Free Software, you can download MILEPOST GCC, use it, study it, and even modify the code if you wish. To make modification easier, the researchers have also created a plugin API called the Interactive Compilation Interface (ICI). For more on how the machine learning process works, visit the MILEPOST website. You can learn a lot about what's going on by reading the MILEPOST FAQ. There is also a mailing list for those who'd like to join the development project and help work on this new generation of intelligent self-tuning compilation tools.

Earlier this year NOAA warned that increased global warming was combining with natural variability in the Arctic and could result in an ice-free Arctic in as little as 30 years, rather than the end of the century as predict by earlier models. This has created a sense of urgency among organizations studying the changes. NOAA and NASA have combined forces with Northrop Grumman to create a specially modified Global Hawk UAV that will make 6 long duration mission over the Arctic and the Pacific ocean to collect data in troposphere and lower stratosphere. The Global Hawk is an autonomous robot that can stay aloft for 31 hours at altitudes up to 65,000 feet. NASA is also using a UAVSAR (Uninhabited Aerial Vehicle Synthetic Aperture Radar) to create highly detailed Arctic ice maps:

Using these data, scientists would also be able to measure the speed, direction and topographic height of ice caps whose sub-glacial bedrock topography is already mapped – thereby providing critical information that can be used to improve models of glacier mechanics.

Meanwhile, Seaglider robots have been deployed off Greenland to make more accurate measurements of Arctic sea currents. Scientist believe the Arctic runoff is already altering the density of sea water in the Labrador Sea, driving critical ocean circulation that affect the global climate. We mentioned last month that another seaglider project has resuled in a new understanding of ocean circulation that should significantly improve the accuracy of climate models. Canada is also deploying two AUVs to scan the seabed to further their claims in the coming UN Convention that will determine which nations get sovereign rights to the new ocean areas forming as the Arctic melts.